Upscale V1 | AI Video Upscaler API

Runway Video Upscaler V1

Enhance your video resolution with Runway's AI-powered upscaling technology. Simply upload a video and get back a higher-resolution version with improved clarity, sharper details, and cleaner edges — no complex settings required.

Why It Looks Great

AI-enhanced detail: Reconstructs fine textures, edges, and details that traditional upscaling cannot recover.
Temporal consistency: Maintains stable quality across frames, minimizing flickering and artifacts.
Motion preservation: Keeps fast action and camera movements smooth without introducing blur.
Artifact reduction: Cleans up compression noise and blocky artifacts from lower-quality sources.
One-click simplicity: No parameters to tune — just upload and upscale.

Parameters

Parameter	Required	Description
video	Yes	Source video file (upload or public URL). Max 10 minutes.

How to Use

Upload your video — drag and drop or paste a public URL.
Run — click the button to start processing.
Download — preview and save your upscaled video.

Pricing

Per-second billing with a 5-second minimum. Maximum video length: 10 minutes.

Metric	Cost
Per second	$0.02
Minimum charge	$0.10 (5 seconds)

Billing Rules

Minimum charge: 5 seconds ($0.10)
Maximum duration: 600 seconds (10 minutes)
Billed duration: Video length in seconds (rounded down), with 5-second minimum
Total cost: Billed duration × $0.02

Examples

Video Length	Billed Duration	Total Cost
3s	5s (minimum)	$0.10
15s	15s	$0.30
1m (60s)	60s	$1.20
5m (300s)	300s	$6.00
10m (600s)	600s (maximum)	$12.00

Best Use Cases

Content Restoration — Upscale old or low-resolution footage for modern displays.
Social Media — Enhance video quality before posting to platforms that compress uploads.
Video Production — Improve B-roll or archival footage for professional projects.
Streaming & Broadcast — Prepare lower-resolution content for HD or 4K delivery.
Personal Archives — Revive old home videos and memories with improved clarity.

Pro Tips for Best Results

Upload the highest-quality source available — avoid heavily compressed inputs when possible.
Keep the original frame rate; avoid re-encoding before upload.
For videos longer than 10 minutes, split into segments and process separately.
Works best on content with clear subjects; extremely noisy or blurry sources may have limited improvement.

Notes

If using a URL, ensure it is publicly accessible. A preview thumbnail in the interface confirms successful loading.
Processing time varies based on video length and current queue load.
For longer videos exceeding the 10-minute limit, split into multiple segments, process each, then merge afterward.

Upscale v1 API — Quick start

Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/runwayml/upscale-v1 with your input as JSON. The endpoint returns a prediction id; poll the prediction endpoint until status flips to completed, then read the output URL from data.outputs[0]. Examples for Upscale v1 below.

HTTP example

# Submit the prediction
curl -X POST "https://api.wavespeed.ai/api/v3/runwayml/upscale-v1" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $WAVESPEED_API_KEY" \
  -d '{
    "video": "https://example.com/your-input.mp4"
}'

# Response includes a prediction id. Poll for the result:
curl -X GET "https://api.wavespeed.ai/api/v3/predictions/{request_id}/result" \
  -H "Authorization: Bearer $WAVESPEED_API_KEY"

# When status is "completed", read the output from data.outputs[0].

Node.js example

// npm install wavespeed
const WaveSpeed = require('wavespeed');

const client = new WaveSpeed(); // reads WAVESPEED_API_KEY from env

const result = await client.run("runwayml/upscale-v1", {
        "video": "https://example.com/your-input.mp4"
});

console.log(result.outputs[0]); // → URL of the generated output

Python example

# pip install wavespeed
import wavespeed

output = wavespeed.run(
    "runwayml/upscale-v1",
    {
    "video": "https://example.com/your-input.mp4"
}
)

print(output["outputs"][0])  # → URL of the generated output

Upscale v1 API — Frequently asked questions

What is the Upscale v1 API?

Upscale v1 is a Runwayml model for upscaling, exposed as a REST API on WaveSpeedAI. RunwayML Upscale V1 upscales videos to 4K via simple file upload, billed at $0.02/sec for fast, high-quality upscaling. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing. You can call it programmatically or try it from the playground above.

How do I call the Upscale v1 API?

POST your input parameters to the model's REST endpoint (shown in the API tab of this playground) with your WaveSpeedAI API key in the Authorization header. Submission returns a prediction ID; poll the prediction endpoint until status flips to "completed", then read the output URL from the result. The playground generates a ready-to-paste code sample in Python, JavaScript, or cURL for whatever inputs you've set. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/runwayml/runwayml-upscale-v1.

How much does Upscale v1 cost per run?

Upscale v1 starts at $0.020 per run. That figure is the base price — the final charge scales with the parameters you set in the form (output size, length, count, references, or whatever knobs this model exposes), so a higher-quality or larger output costs more than a minimal one. The exact cost for your current input is shown live next to the Generate button before you submit, and the actual per-call charge is recorded on the prediction afterwards.

What inputs does Upscale v1 accept?

Key inputs: `video`. The full JSON schema (types, defaults, allowed values) is rendered above the Generate button and mirrored in the API reference at https://wavespeed.ai/docs/docs-api/runwayml/runwayml-upscale-v1.

How long does Upscale v1 take to generate?

Average end-to-end generation time on WaveSpeedAI is around 505 seconds per request — measured across recent runs. Queue time scales with global demand; live status is visible in the prediction record.

Can I use Upscale v1 outputs commercially?

Commercial usage rights depend on the model's license, set by its provider (Runwayml). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.

ExemplosVer todos

Modelos relacionados

README